我如何在 TensorFlow 中使用批量标准化? [英] How could I use batch normalization in TensorFlow?

问题描述

我想在 TensorFlow 中使用批量标准化.我在 core/中找到了相关的 C++ 源代码ops/nn_ops.cc.但是，我没有在 tensorflow.org 上找到它.

I would like to use batch normalization in TensorFlow. I found the related C++ source code in core/ops/nn_ops.cc. However, I did not find it documented on tensorflow.org.

BN 在 MLP 和 CNN 中有不同的语义，所以我不确定这个 BN 到底是做什么的.

BN has different semantics in MLP and CNN, so I am not sure what exactly this BN does.

我也没有找到名为 MovingMoments 的方法.

I did not find a method called MovingMoments either.

推荐答案

2016 年 7 月更新 在 TensorFlow 中使用批处理规范化的最简单方法是通过 contrib/layers, tflearn 或 slim.

Update July 2016 The easiest way to use batch normalization in TensorFlow is through the higher-level interfaces provided in either contrib/layers, tflearn, or slim.

如果你想自己动手做之前的回答:自发布以来，此文档字符串有所改进 - 请参阅 主分支中的文档注释 而不是您找到的那个.它特别澄清了它是 tf.nn.moments 的输出.

Previous answer if you want to DIY: The documentation string for this has improved since the release - see the docs comment in the master branch instead of the one you found. It clarifies, in particular, that it's the output from tf.nn.moments.

您可以在 batch_norm 测试代码.对于更真实的使用示例，我在帮助类下方包含了我为自己使用而草拟的使用说明(不提供任何保证！):

You can see a very simple example of its use in the batch_norm test code. For a more real-world use example, I've included below the helper class and use notes that I scribbled up for my own use (no warranty provided!):

"""A helper class for managing batch normalization state.                   

This class is designed to simplify adding batch normalization               
(http://arxiv.org/pdf/1502.03167v3.pdf) to your model by                    
managing the state variables associated with it.                            

Important use note:  The function get_assigner() returns                    
an op that must be executed to save the updated state.                      
A suggested way to do this is to make execution of the                      
model optimizer force it, e.g., by:                                         

  update_assignments = tf.group(bn1.get_assigner(),                         
                                bn2.get_assigner())                         
  with tf.control_dependencies([optimizer]):                                
    optimizer = tf.group(update_assignments)                                

"""

import tensorflow as tf


class ConvolutionalBatchNormalizer(object):
  """Helper class that groups the normalization logic and variables.        

  Use:                                                                      
      ewma = tf.train.ExponentialMovingAverage(decay=0.99)                  
      bn = ConvolutionalBatchNormalizer(depth, 0.001, ewma, True)           
      update_assignments = bn.get_assigner()                                
      x = bn.normalize(y, train=training?)                                  
      (the output x will be batch-normalized).                              
  """

  def __init__(self, depth, epsilon, ewma_trainer, scale_after_norm):
    self.mean = tf.Variable(tf.constant(0.0, shape=[depth]),
                            trainable=False)
    self.variance = tf.Variable(tf.constant(1.0, shape=[depth]),
                                trainable=False)
    self.beta = tf.Variable(tf.constant(0.0, shape=[depth]))
    self.gamma = tf.Variable(tf.constant(1.0, shape=[depth]))
    self.ewma_trainer = ewma_trainer
    self.epsilon = epsilon
    self.scale_after_norm = scale_after_norm

  def get_assigner(self):
    """Returns an EWMA apply op that must be invoked after optimization."""
    return self.ewma_trainer.apply([self.mean, self.variance])

  def normalize(self, x, train=True):
    """Returns a batch-normalized version of x."""
    if train:
      mean, variance = tf.nn.moments(x, [0, 1, 2])
      assign_mean = self.mean.assign(mean)
      assign_variance = self.variance.assign(variance)
      with tf.control_dependencies([assign_mean, assign_variance]):
        return tf.nn.batch_norm_with_global_normalization(
            x, mean, variance, self.beta, self.gamma,
            self.epsilon, self.scale_after_norm)
    else:
      mean = self.ewma_trainer.average(self.mean)
      variance = self.ewma_trainer.average(self.variance)
      local_beta = tf.identity(self.beta)
      local_gamma = tf.identity(self.gamma)
      return tf.nn.batch_norm_with_global_normalization(
          x, mean, variance, local_beta, local_gamma,
          self.epsilon, self.scale_after_norm)

请注意，我将其称为 ConvolutionalBatchNormalizer，因为它使用 tf.nn.moments 对轴 0、1 和 2 求和，而对于非卷积使用，您可能只需要轴 0.

Note that I called it a ConvolutionalBatchNormalizer because it pins the use of tf.nn.moments to sum across axes 0, 1, and 2, whereas for non-convolutional use you might only want axis 0.

如果您使用它，请提供反馈.

Feedback appreciated if you use it.

这篇关于我如何在 TensorFlow 中使用批量标准化?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！